19 May 2021 in IEEE Internet of Things Journal
This article studies the joint optimization problem of computation offloading and resource allocation (JCORA) in mobile-edge computing (MEC). Deep reinforcement learning (DRL) is one of the ideal techniques for addressing the dynamic JCORA problem. However, it is still challenging to adapt traditional DRL methods for the problem since they usually lead to slow and unstable convergence in model training. To this end, we propose a temporal attentional deterministic policy gradient (TADPG) to tackle JCORA. Based on the deep deterministic policy gradient (DDPG), TADPG has two significant features. First, a temporal feature extraction network consisting of a 1-D convolution (Conv1D) residual block and an attentional long short-term memory (LSTM) network is designed, which is beneficial to high-quality state representation and function approximation. Second, a rank-based prioritized experience replay (rPER) method is devised to accelerate and stabilize the convergence of model training. Experimental results demonstrate that the decentralized TADPG-based mechanism can achieve more efficient JCORA performance than the centralized one, and the proposed TADPG outperforms a number of state-of-the-art DRL agents in terms of the task completion time and energy consumption.
1 October 2021 in Knowledge-Based Systems
21 September 2022 in IEEE Transactions on Mobile Computing
This paper studies the trajectory control and task offloading (TCTO) problem in an unmanned aerial vehicle (UAV)-assisted mobile edge computing system, where a UAV flies along a planned trajectory to collect computation tasks from smart devices (SDs). We consider a scenario that SDs are not directly connected by the base station (BS) and the UAV has two roles to play: MEC server or wireless relay. The UAV makes task offloading decisions online, in which the collected tasks can be executed locally on the UAV or offloaded to the BS for remote processing. The TCTO problem involves multi-objective optimization as its objectives are to minimize the task delay and the UAV's energy consumption, and maximize the number of tasks collected by the UAV, simultaneously. This problem is challenging because the three objectives conflict with each other. The existing reinforcement learning (RL) algorithms, either single-objective RLs or single-policy multi-objective RLs, cannot well address the problem since they cannot output multiple policies for various preferences (i.e. weights) across objectives in a single run. An evolutionary multi-objective RL (EMORL) algorithm is applied to address the TCTO problem. We improve the multi-task multi-objective proximal policy optimization of the original EMORL by retaining all new learning tasks in the offspring population, which can preserve promissing learning tasks. The simulation results demonstrate that the proposed algorithm can obtain more excellent non-dominated policies by striking a balance between the three objectives regarding policy quality, compared with two evolutionary algorithms, two multi-policy RL algorithms, and the original EMORL.
9 January 2024 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Multivariate time series classification (MTSC) based on deep learning (DL) has attracted increasingly more research attention. The performance of a DL-based MTSC algorithm is heavily dependent on the quality of the learned representations providing semantic information for downstream tasks, e.g., classification. Hence, a model’s representation learning ability is critical for enhancing its performance. This article proposes a densely knowledge-aware network (DKN) for MTSC. The DKN’s feature extractor consists of a residual multihead convolutional network (ResMulti) and a transformer-based network (Trans), called ResMulti-Trans. ResMulti has five residual multihead blocks for capturing the local patterns of data while Trans has three transformer blocks for extracting the global patterns of data. Besides, to enable dense mutual supervision between lower-and higher-level semantic information, this article adapts densely dual self-distillation (DDSD) for mining rich regularizations and relationships hidden in the data. Experimental results show that compared with 5 state-of-the-art self-distillation variants, the proposed DDSD obtains 13/4/13 in terms of “win”/“tie”/“lose” and gains the lowest-AVG_rank score. In particular, compared with pure ResMulti-Trans, DKN results in 20/1/9 regarding win/tie/lose. Last but not least, DKN overweighs 18 existing MTSC algorithms on 10 UEA2018 datasets and achieves the lowest-AVG_rank score.
29 August 2023 in IEEE Transactions on Emerging Topics in Computational Intelligence
Recently, contrastive learning (CL) is a promising way of learning discriminative representations from time series data. In the representation hierarchy, semantic information extracted from lower levels is the basis of that captured from higher levels. Low-level semantic information is essential and should be considered in the CL process. However, the existing CL algorithms mainly focus on the similarity of high-level semantic information. Considering the similarity of low-level semantic information may improve the performance of CL. To this end, we present a deep contrastive representation learning with self-distillation (DCRLS) for the time series domain. DCRLS gracefully combine data augmentation, deep contrastive learning, and self distillation. Our data augmentation provides different views from the same sample as the input of DCRLS. Unlike most CL algorithms that concentrate on high-level semantic information only, our deep contrastive learning also considers the contrast similarity of low-level semantic information between peer residual blocks. Our self distillation promotes knowledge flow from high-level to low-level blocks to help regularize DCRLS in the knowledge transfer process. The experimental results demonstrate that the DCRLS-based structures achieve excellent performance on classification and clustering on 36 UCR2018 datasets.
27 December 2023 in IEEE Transactions on Neural Networks and Learning Systems
This article proposes a semi-supervised contrastive capsule transformer method with feature-based knowledge distillation (KD) that simplifies the existing semisupervised learning (SSL) techniques for wearable human activity recognition (HAR), called CapMatch. CapMatch gracefully hybridizes supervised learning and unsupervised learning to extract rich representations from input data. In unsupervised learning, CapMatch leverages the pseudolabeling, contrastive learning (CL), and feature-based KD techniques to construct similarity learning on lower and higher level semantic information extracted from two augmentation versions of the data“, weak” and “timecut”, to recognize the relationships among the obtained features of classes in the unlabeled data. CapMatch combines the outputs of the weak-and timecut-augmented models to form pseudolabeling and thus CL. Meanwhile, CapMatch uses the feature-based KD to transfer knowledge from the intermediate layers of the weak-augmented model to those of the timecut-augmented model. To effectively capture both local and global patterns of HAR data, we design a capsule transformer network consisting of four capsule-based transformer blocks and one routing layer. Experimental results show that compared with a number of state-of-the-art semi-supervised and supervised algorithms, the proposed CapMatch achieves decent performance on three commonly used HAR datasets, namely, HAPT, WISDM, and UCI_HAR. With only 10% of data labeled, CapMatch achieves $F_{1}$ values of higher than 85.00% on these datasets, outperforming 14 semi-supervised algorithms. When the proportion of labeled data reaches 30%, CapMatch obtains $F_{1}$ values of no lower than 88.00% on the datasets above, which is better than several classical supervised algorithms, e.g., decision tree and $k$ -nearest neighbor (KNN).